The convergence rate of the Least Mean Squares (LMS) algorithm is poor whenever the adaptive filter input auto-correlation matrix is ill-conditioned. In this paper we propose a new LMS algorithm to alleviate this problem. It uses a data dependent signal transformation. The algorithm tracks the subspaces corresponding to clusters of eigenvalues of the auto-correlation matrix of the input to the adaptive filter, which have the same order of magnitude. The algorithm up-dates the projection of the tap weights of the adaptive filter onto each subspace using LMS algorithms with different step sizes. The technique also permits adaptation only in those subspaces, which contain strong signal components leading to a lower excess Mean Squared Error (MSE) as compared to traditional algorithms.
|Original language||English (US)|
|Journal||ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings|
|State||Published - 1994|
|Event||Proceedings of the 1994 IEEE International Conference on Acoustics, Speech and Signal Processing. Part 2 (of 6) - Adelaide, Aust|
Duration: Apr 19 1994 → Apr 22 1994
Bibliographical noteFunding Information:
THIS WORK WAS SUPPORTED IN PART BY ONR UNDER GRANT N00014-92-J-1678 AND AFOSR UNDER GRANT AF/F49620-93-1-0151DEF
© 1994 IEEE.